State of vLLM 2026 | Inferact | Ray Summit 2026

vLLM's engine, ecosystem, and contributor base are all growing fast. This talk surveys where the project stands and the roadmap ahead. At Ray Summit 2026, Woosuk Kwon and Zachary Xi of Inferact cover the Flat Model and Model Runner V2 migrations, disaggregated serving with multi-tier KV offloading, speculative decoding toward 1000+ TPS, and production-grade quantized KV cache compression, plus the infrastructure, CI, and security work needed to support a rapidly growing contributor base and the expanding ecosystem around quantization, speculation, RL frameworks, and vLLM-Omni for real-time multimodal models. You'll leave current on vLLM across its engine, ecosystem, and open-source practices. This session was part of the first vLLM Conference at Ray Summit, hosted by Inferact. Liked this video? Check out other Ray Summit vLLM session recordings: https://www.youtube.com/playlist?list=PLXMguE8Nc9o4 Subscribe to our YouTube channel to stay up-to-date on the future of AI: https://www.youtube.com/c/anyscale 🔗 Connect with us: LinkedIn: https://www.linkedin.com/company/joinanyscale/ X: https://x.com/anyscalecompute Website: https://www.anyscale.com/